Most current methods for multi-hop question answering (QA) over knowledge graphs (KGs) only provide final conclusive answers without explanations, such as a set of KG entities that is difficult for normal users to review and comprehend. This issue severely limits the application of KG-based QA in real-world scenarios. However, it is non-trivial to solve due to two challenges: First, annotations of reasoning chains of multi-hop questions, which could serve as supervision for explanation generation, are usually lacking. Second, it is difficult to maintain high efficiency when explicit KG triples need to be retrieved to generate explanations. In this paper, we propose a novel Graph Neural Network-based Two-Step Reasoning model (GNN2R) to solve this issue. GNN2R can provide both final answers and reasoning subgraphs as a rationale behind final answers efficiently with only weak supervision that is available through question-final answer pairs. We extensively evaluated GNN2R with detailed analyses in experiments. The results demonstrate that, in terms of effectiveness, efficiency, and quality of generated explanations, GNN2R outperforms existing state-of-the-art methods that are applicable to this task. Our code and pre-trained models are available at https://github.com/ruijie-wang-uzh/GNN2R.

翻译：当前大多数基于知识图谱的多跳问答方法仅提供最终结论性答案，而缺乏解释——例如难以被普通用户审查和理解的知识图谱实体集合。这一问题严重限制了知识图谱问答在真实场景中的应用。然而，解决该问题面临两大挑战：首先，多跳问题的推理链标注数据（可作为解释生成的监督信号）通常缺失；其次，在需要显式检索知识图谱三元组以生成解释时，难以保持高效率。本文提出一种新颖的基于图神经网络的两步推理模型GNN2R来解决该问题。GNN2R仅需通过问题-答案对即可获得的弱监督信号，就能高效地同时提供最终答案和作为答案理据的推理子图。我们通过实验对GNN2R进行了全面评估与详细分析。结果表明，在生成解释的有效性、效率及质量方面，GNN2R优于现有适用于该任务的最优方法。我们的代码和预训练模型已在https://github.com/ruijie-wang-uzh/GNN2R上公开。